Method of detecting and tracking groups of people

Abstract

A computer-interfaced camera system identifies and tracks groups of socially interrelated people. The system can be used, for example, to track people as they wait in a checkout line or at a service counter. In a preferred implementation, each recorded camera frame is segmented into foreground regions containing several people. The foreground regions are further segmented into individuals using temporal segmentation analysis. Once an individual person is detected, an appearance model based on color and edge density in conjunction with a mean-shift tracker is used to recover the person's trajectory. Groups of people are determined by analyzing inter-person distances over time.

Description

TECHNICAL FIELD[0001]The invention is in the field of video surveillance, and more particularly, the invention relates to the ability to detect and track groups of people.BACKGROUND[0002]Recent advances in camera technology and increased processor power have enabled surveillance systems to monitor human activities in real-time. (See, for example, D. M. Gavrila, “The visual analysis of human movement: a survey”, Computer Vision and Image Understanding, vol. 73, pp. 82-98, 1999.) Surveillance cameras are commonly used in stores, hallways, and along streets for security applications such as crime-prevention or post-crime investigations. On the other hand, retail store managers are also interested in using cameras to extract business intelligence information. Retailers desire real-time information about customer traffic patterns, queue lengths, and check-out waiting times to improve operational efficiency and customer satisfaction. They are more interested in determining the number of s...

AI Technical Summary

Benefits of technology

[0008]In a preferred implementation of the invention, retail managers may use such information about groups to help them manage customer traffic patterns, queue lengths, and waiting times. For example, operational efficiency and customer satisfaction may be improved when a manager opens up an additional checkout lane if the number of groups detected in one of the checkout lanes exceeds a predetermined value. Additionally, the activities of the cashier may be monitored to determine when shopping transactions start and end and thereby more precisely establish the number of groups in a checkout lane.

Problems solved by technology

However, these investigators have not addressed the issue of detecting and locating people as they move as a group.

The ability to visually detect and track groups of people and their activities in crowded areas therefore remains an important problem.

This problem is complicated by the fact that when people interact with each other, they are often partially or totally occluded.

Images